submit_swap

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare readOnlyHint=false, destructiveHint=false and openWorldHint=false; the description adds substantial context beyond that: outputs are new job artifacts (non-destructive by construction), H.264 video with AAC first-audio-stream encoding, the Inswapper128 preview default, and a real operational constraint that GPU jobs run one at a time. It does not say whether submission returns immediately with a job handle or blocks, nor what identifiers come back, which is why it stops short of 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Dense but well front-loaded: purpose first, then mode semantics, then output behavior, then constraints. Every sentence carries information, though the run of constraints at the end is terse to the point of feeling compressed and could be split for readability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need no prose, and for an 8-parameter write tool the description covers purpose, mode semantics, output format, concurrency and rejection conditions well. The remaining gap is the trio of undocumented inputs (job_id, controls, media_path) for a schema with zero description coverage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry the parameter burden and it only partly does. It explains the mode-dependent meaning of `frame`, `start_frame` and `max_frames` (including that None means through the end), but `media_path`, `job_id`, `controls` and the structure of `mappings` receive no explanation in either place.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete verb and resource ('Queue an image/frame preview or CFR video render') and immediately splits the two modes, so an agent knows exactly which operation it is committing to. It is clearly distinct from inspection siblings like inspect_media or detect_faces, which analyze rather than queue work.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly distinguishes when to use preview ('processes `frame`') versus render ('processes `start_frame` and at most `max_frames`'), names the prerequisite tool ('Consult get_settings before changing parameters'), and routes unsupported inputs elsewhere ('Renders reject VFR, nonzero start times, odd dimensions and rotation; use normalize_media'). Both the when-to-use and when-not-to-use paths are covered with named alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.